State Estimation of Fractional-Order Memristor-Based Neural Networks with Probabilistic Time-Varying Delay

This paper proposed a state estimator to track the states of fractional-order memeristor-based neural networks (FMNNs) with probabilistic time-varying delay which was first introduced into FMNNs. Lyapunov functionals, interval matrix method and fractional-order comparison principle are employed to acquire new linear matrix inequalities (LMIs) criteria associated with the probability of the time delay, which ensure the asymptotically stability in the mean square of the estimation error system. Finally, a numerical example was given to validate the correctness of the theoretical outcomes.